/*在SetImage或者TesseractRect之后，获取内部阈值后图像的一个COPY*/
  Pix* GetThresholdedImage();

  /*获得版面分析的结果（layout analysis）
    在分析之前或者之后调用.*/
  Boxa* GetRegions(Pixa** pixa);

  /**
   * Get the textlines as a leptonica-style
   * Boxa, Pixa pair, in reading order.
   * Can be called before or after Recognize.
   * If blockids is not NULL, the block-id of each line is also returned
   * as an array of one element per line. delete [] after use.
   */
  Boxa* GetTextlines(Pixa** pixa, int** blockids);

  /**
   * Get the words as a leptonica-style
   * Boxa, Pixa pair, in reading order.
   * Can be called before or after Recognize.
   */
  Boxa* GetWords(Pixa** pixa);

  // Gets the individual connected (text) components (created
  // after pages segmentation step, but before recognition)
  // as a leptonica-style Boxa, Pixa pair, in reading order.
  // Can be called before or after Recognize.
  // Note: the caller is responsible for calling boxaDestroy()
  // on the returned Boxa array and pixaDestroy() on cc array.
  Boxa* GetConnectedComponents(Pixa** cc);

  // Get the given level kind of components (block, textline, word etc.) as a
  // leptonica-style Boxa, Pixa pair, in reading order.
  // Can be called before or after Recognize.
  // If blockids is not NULL, the block-id of each component is also returned
  // as an array of one element per component. delete [] after use.
  Boxa* GetComponentImages(PageIteratorLevel level,
                           Pixa** pixa, int** blockids);

#include "stdafx.h"

#include "allheaders.h"
#include "baseapi.h"
#include "resultiterator.h"
#include "strngs.h"
#include "blobs.h"

#include "cv.h"
#include "highgui.h"
#include "cxcore.h"

#include "stdlib.h"
using namespace  tesseract;

int _tmain(int argc, _TCHAR* argv[])

{
	STRING text_out;

	IplImage *iplimg =  NULL;
	iplimg = cvLoadImage("1.jpg");
	tesseract::TessBaseAPI  api;
	//api.SetVariable("tessedit_char_whitelist", "0123456789abcdefghijklmnopqrstuvwsyzABCDEFGHIJKLMNOPQRSTUVWXYZ");
	//SetVariable("tessedit_char_blacklist", "xyz"); to ignore x, y and z.
	//api.SetVariable("classify_bln_numeric_mode", "123456789");

	api.Init("C:\\BuildFolder\\tesseract-3.01\\tessdata", NULL);
	//api.SetPageSegMode(PSM_SINGLE_BLOCK);
	api.SetImage((unsigned char*)(iplimg->imageData), 
						iplimg->width, iplimg->height,iplimg->nChannels  , iplimg->widthStep);//设置图像
	char* text = api.GetUTF8Text();//识别图像中的文字

	printf("%s\n","获得的结果");
	printf("%s\n",text);
	FILE* fout = fopen("txt_file.TXT", "w");


	//fwrite(text_out.string(), 1, text_out.length(), fout);//将识别结果写入输出文件

	fprintf(fout,"%s\n","获得的结果");
	fprintf(fout,"%s\n",text);
	fclose(fout);

	
	UINT d = api.MeanTextConf();
	fprintf(fout,"%d\n",d);
	printf("%d\n",d);

	int *gg = api.AllWordConfidences();

	while (*gg != '\0')
	{
		printf("%d\n",*gg);
		gg ++ ;
	}


	getchar();

	api.Clear();
	api.End();
	return 0;

}